BERT: a sentiment analysis odyssey

Alaparthi, Shivaji; Mishra, Manit

doi:10.1057/s41270-021-00109-8

Cited by 80 publications

(46 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Specifically, comments were classified using Bidirectional Encoder Representations from Transformers (BERT), a transformer-based natural language machine learning classification algorithm with outstanding performance on subtle classification tasks because it encodes both semantics and the rich latent structure of sentences ( 5 , 6 ). The superiority of BERT over other machine learning natural language classification models has been repeatedly established in varied real-world social science datasets ( 7 – 12 ).…”

Section: Methodsmentioning

confidence: 99%

Widespread use of National Academies consensus reports by the American public

Hicks

Zullo

Doshi

et al. 2022

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

In seeking to understand how to protect the public information sphere from corruption, researchers understandably focus on dysfunction. However, parts of the public information ecosystem function very well, and understanding this as well will help in protecting and developing existing strengths. Here, we address this gap, focusing on public engagement with high-quality science-based information, consensus reports of the National Academies of Science, Engineering, and Medicine (NASEM). Attending to public use is important to justify public investment in producing and making freely available high-quality, scientifically based reports. We deploy Bidirectional Encoder Representations from Transformers (BERT), a high-performing, supervised machine learning model, to classify 1.6 million comments left by US downloaders of National Academies reports responding to a prompt asking how they intended to use the report. The results provide detailed, nationwide evidence of how the public uses open access scientifically based information. We find half of reported use to be academic—research, teaching, or studying. The other half reveals adults across the country seeking the highest-quality information to improve how they do their job, to help family members, to satisfy their curiosity, and to learn. Our results establish the existence of demand for high-quality information by the public and that such knowledge is widely deployed to improve provision of services. Knowing the importance of such information, policy makers can be encouraged to protect it.

show abstract

Section: Methodsmentioning

confidence: 99%

Widespread use of National Academies consensus reports by the American public

Hicks

Zullo

Doshi

et al. 2022

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…Regarding natural language processing (NLP), a tool that has been widely used is the so-called BERT (Devlin et al, 2018 ). The creators of BERT, members of a research team working for Google, mention that BERT incorporates a training database of writings with more than a billion words (see Devlin et al, 2018 ), a feature that has helped BERT reach success in more than 90% of the classification tasks (e.g., Alaparthi and Mishra, 2021 ). Note, however, that even well-trained judges do not agree with each other in rating setiment from personal stories (Tausczik and Pennebaker, 2010 , p. 26).…”

Section: Methods and Proceduresmentioning

confidence: 99%

Negative Perception of the COVID-19 Pandemic Is Dropping: Evidence From Twitter Posts

et al. 2021

View full text Add to dashboard Cite

The COVID-19 pandemic hit hard society, strongly affecting the emotions of the people and wellbeing. It is difficult to measure how the pandemic has affected the sentiment of the people, not to mention how people responded to the dramatic events that took place during the pandemic. This study contributes to this discussion by showing that the negative perception of the people of the COVID-19 pandemic is dropping. By negative perception, we mean the number of negative words the users of Twitter, a social media platform, employ in their online posts. Seen as aggregate, Twitter users are using less and less negative words as the pandemic evolves. The conclusion that the negative perception is dropping comes from a careful analysis we made in the contents of the COVID-19 Twitter chatter dataset, a comprehensive database accounting for more than 1 billion posts generated during the pandemic. We explore why the negativity of the people decreases, making connections with psychological traits such as psychophysical numbing, reappraisal, suppression, and resilience. In particular, we show that the negative perception decreased intensively when the vaccination campaign started in the USA, Canada, and the UK and has remained to decrease steadily since then. This finding led us to conclude that vaccination plays a key role in dropping the negativity of the people, thus promoting their psychological wellbeing.

show abstract

“…Zhao et al [23] proposed a knowledge-based language representation model BERT for aspect-based sentiment analysis.The main feature of this model is the integration of external emotional domain knowledge into BERT, which can obtain better performance with a small amount of training data. Alaparthi et al [24] compared the relative effectiveness of four sentiment analysis techniques and proved the undisputed advantage of BERT in text sentiment classification. Yenduri et al [25] proposed a novel customized BERT-oriented model for Twitter sentiment classification.…”

Section: Research On Sentiment Analysis Based On Transformermentioning

confidence: 99%

“…BERT [24]: A powerful and open source text pre-training model based on the transformer structure. 6.…”

mentioning

confidence: 99%

Weibo Text Sentiment Analysis Based on BERT and Deep Learning

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

With the rapid increase of public opinion data, the technology of Weibo text sentiment analysis plays a more and more significant role in monitoring network public opinion. Due to the sparseness and high-dimensionality of text data and the complex semantics of natural language, sentiment analysis tasks face tremendous challenges. To solve the above problems, this paper proposes a new model based on BERT and deep learning for Weibo text sentiment analysis. Specifically, first using BERT to represent the text with dynamic word vectors and using the processed sentiment dictionary to enhance the sentiment features of the vectors; then adopting the BiLSTM to extract the contextual features of the text, the processed vector representation is weighted by the attention mechanism. After weighting, using the CNN to extract the important local sentiment features in the text, finally the processed sentiment feature representation is classified. A comparative experiment was conducted on the Weibo text dataset collected during the COVID-19 epidemic; the results showed that the performance of the proposed model was significantly improved compared with other similar models.

show abstract

BERT: a sentiment analysis odyssey

Cited by 80 publications

References 44 publications

Widespread use of National Academies consensus reports by the American public

Widespread use of National Academies consensus reports by the American public

Negative Perception of the COVID-19 Pandemic Is Dropping: Evidence From Twitter Posts

Weibo Text Sentiment Analysis Based on BERT and Deep Learning

Contact Info

Product

Resources

About